Spectro-Temporal Features for Howling Frequency Detection

被引：0

作者：

Lee, Jae-Won ^{[2
]}

Choi, Seung Ho ^{[1
]}

机构：

[1] Seoul Natl Univ Sci & Technol, Dept Elect & IT Media Engn, Seoul 139743, South Korea

[2] Seoul Natl Univ Sci & Technol, Grad Sch NID Fus Technol, Seoul 139743, South Korea

来源：

COMPUTER APPLICATIONS FOR WEB, HUMAN COMPUTER INTERACTION, SIGNAL AND IMAGE PROCESSING AND PATTERN RECOGNITION | 2012年 / 342卷

关键词：

Howling frequency detection; Spectro-temporal feature; Acoustic feedback circuit;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The howling varies depending on the room environment and it is difficult to predict the howling. In this research work, we develop spectro-temporal features for howling frequency detection. For the detection of howling frequency, several techniques have been developed such as least mean square method. The proposed approach is based on statistical properties of temporal power spectra, which requires less computational complexity than conventional methods. The proposed method is experimentally shown to be suitable for applications in sound systems.

引用

页码：25 / +

页数：2

共 8 条

[1] [Anonymous], 2010, P IEEE WORKSH NONL D
[2] Gil-Cacho P., 2009, P EUSIPCO, P2574
[3] Kuto S. M., 2004, IEEE 7 INT C SIGN PR, P579
[4] Lee J.-W., 2011, FGCN 2011 2, V266, P154
[5] A MINIMAL PARAMETER ADAPTIVE NOTCH FILTER WITH CONSTRAINED POLES AND ZEROS
NEHORAI, A
[J]. IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1985, 33 (04): : 983 - 996
[6] Schroeder M. R., 1932, J ACOUST SOC AM, V36, P1718
[7] THEORY OF HOWLBACK IN REVERBERANT ROOMS
WATERHOUSE, RV
[J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 1965, 37 (05) : 921 - +
[8] Wei J., 2003, IEEE INT S CIRC SYST, V4, P409

← 1 →